3 Commits

Author	SHA1	Message	Date
Benjamin Admin	198a0b2a0d	Fix: Use /synthesize-direct for correct language selection ... /synthesize always used the German model. /synthesize-direct uses Edge TTS (with language-aware voice selection) and falls back to Piper with the correct model (Thorsten DE / Lessac EN). Also cleared audio cache to purge wrongly-generated files. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-26 23:46:40 +02:00
Benjamin Admin	0f0bbc3dc0	Switch AudioButton to Piper TTS (Thorsten/Lessac voices) ... AudioButton now tries Piper TTS via /api/vocabulary/tts endpoint first, falls back to Browser Web Speech API if unavailable. Backend: New GET /api/vocabulary/tts?text=...&lang=de endpoint. audio_service.py: Fixed presigned URL flow for MinIO download. This gives the same high-quality voice as the Investor Agent in the pitch deck (Thorsten DE / Lessac EN, MIT license). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-26 23:17:39 +02:00
Benjamin Admin	cba877c65a	Restructure: Move final 16 root files into packages (backend-lehrer) ... classroom/ (+2): state_engine_api, state_engine_models vocabulary/ (2): api, db worksheets/ (2): api, models services/ (+6): audio, email, translation, claude_vision, ai_processor, story_generator api/ (4): school, klausur_proxy, progress, user_language Only main.py + config.py remain at root. 16 shims added. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-25 22:50:37 +02:00